How to Use the Dropbox Paper MCP in LlamaIndex

Q: Can LlamaIndex index metadata from my Dropbox Paper files?

Yes, the agent can call getmetadata to extract file names, paths, and update times. This metadata is stored alongside the vector embeddings, allowing you to filter search results by date or folder.

Q: How do I limit which Dropbox Paper folders LlamaIndex can access?

You can apply the allowedtools filter during client setup to restrict access. This prevents the agent from calling tools like deletefile or browsing folders outside of your designated workspace.

Q: Can I use Dropbox Paper with LlamaIndex for multi-document RAG?

Yes, your agent can run searchfiles to gather relevant documents, read their content, and index them into a temporary vector store to answer queries that span multiple project files.

Q: Is my Dropbox Paper account metadata safe during LlamaIndex indexing?

Yes, your account profile fetched via getaccount and storage metrics from getspaceusage remain entirely private. The MCP connection runs in a secure, ephemeral sandbox that never exposes your credentials to external LLM APIs.

Index your Dropbox Paper docs directly into LlamaIndex vector stores using this high-performance MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dropbox Paper MCP to LlamaIndex

Create your Vinkius account to connect Dropbox Paper to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Dropbox Paper with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounding RAG pipelines in live Dropbox Paper docs

Stop relying on stale static exports for your retrieval-augmented generation. This MCP server lets LlamaIndex query your live workspace using `search_files`, converting raw Paper documents into searchable vector embeddings on the fly. When your agent needs to answer a user query, it calls `get_metadata` to verify the document's last-modified timestamp. This ensures your index only uses the latest team updates, preventing the LLM from hallucinating outdated information.

Dynamic knowledge ingestion via LlamaIndex MCP tools

Building an active knowledge base requires constant updates as files move. Your LlamaIndex agent can use `list_files` and `list_files_continue` to scan your directories and automatically index new content as it appears. If a document is archived, the agent detects the change using `list_shared_links` and updates the index accordingly. You get a self-cleaning knowledge base that reflects the actual state of your team's shared folders.

Writing structured agent outputs back to Dropbox Paper

Your LlamaIndex agents can do more than just read data. By exposing `create_document`, the agent can compile synthesis reports from its vector search and write them directly back to your workspace as clean Markdown files. If the report needs to go into a specific shared space, the agent runs `list_shared_folders` to find the correct destination and `move_file` to place it there. This closes the loop between information retrieval and document creation.

Setup guide

Set up Dropbox Paper MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Dropbox Paper MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Dropbox Paper tools.",
)
response = await agent.run("List recent Dropbox Paper data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dropbox Paper. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Dropbox Paper now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Dropbox Paper MCP in LlamaIndex

Use llama-index-tools-mcp to initialize the BasicMCPClient. Wrap it in McpToolSpec and call to_tool_list_async to convert the Dropbox Paper endpoints into tools your agent can execute.

Yes, the agent can call `get_metadata` to extract file names, paths, and update times. This metadata is stored alongside the vector embeddings, allowing you to filter search results by date or folder.

You can apply the allowed_tools filter during client setup to restrict access. This prevents the agent from calling tools like `delete_file` or browsing folders outside of your designated workspace.

Yes, your agent can run `search_files` to gather relevant documents, read their content, and index them into a temporary vector store to answer queries that span multiple project files.

Yes, your account profile fetched via `get_account` and storage metrics from `get_space_usage` remain entirely private. The MCP connection runs in a secure, ephemeral sandbox that never exposes your credentials to external LLM APIs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript